A new formulation for composing discrete generative processes enables precise control over novel condition combinations in image generation, cutting error rates by 63% and speeding up inference.
Compositional generative inverse design.arXiv preprint arXiv:2401.13171
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A derived formulation for composing discrete probabilistic generative processes enables novel condition combinations in image generation, yielding 63.4% relative error reduction and FID gains on CLEVR and FFHQ datasets.
citing papers explorer
-
Controllable Image Generation with Composed Parallel Token Prediction
A new formulation for composing discrete generative processes enables precise control over novel condition combinations in image generation, cutting error rates by 63% and speeding up inference.
-
Controllable Image Generation with Composed Parallel Token Prediction
A derived formulation for composing discrete probabilistic generative processes enables novel condition combinations in image generation, yielding 63.4% relative error reduction and FID gains on CLEVR and FFHQ datasets.